INDEX

Explanations

phrases and terms related to business strategies and planning

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stones

-0.17

erman

-0.17

pare

-0.16

ances

-0.16

stone

-0.15

sure

-0.15

alten

-0.15

UTE

-0.15

OfString

-0.15

ê¸ī

-0.14

POSITIVE LOGITS

çķ¥

0.20

ically

0.18

andle

0.16

tical

0.16

../../../

0.16

Fav

0.15

tero

0.15

olo

0.14

strup

0.14

Activations Density 0.024%

phrases and terms related to business strategies and planning

No Comments

No Known Activations